[RecSys'22] Off-Policy Actor-critic for Recommender Systems

March 9, 2024, 9:38 p.m.

추천시스템에 강화학습 모델인 actor critic을 적용시킨 논문

오랜만에 논문리뷰

LLMs for User Interest Exploration in Large-scale Recommendation Systems

June 14, 2024, 1:44 p.m.

E-commerce에서 LLM 을 활용하는것에 대한 효과

google deepmind 논문

[SIGIR'24] Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models

Oct. 31, 2024, 9:08 a.m.

setwise prompting 기법으로 Zero-shot document ranking 즉, LLM-based zero-shot ranking task에서 높은 효율성과 우위 달성한 방법. Re-ranking에 초점이 맞춰짐